Drawing Multiple Augmentation Samples Per Image
— AK (@ak92501) May 28, 2021
During Training Efficiently Decreases Test Error
pdf: https://t.co/zwS8DT9Km0
abs: https://t.co/8xxFUi2nay
ImageNet SOTA of 86.8% top-1 accuracy after just 34 epochs of training with an NFNet-F5 using the SAM optimizer pic.twitter.com/AhDVnLSef4
CogView: Mastering Text-to-Image Generation via Transformers
— AK (@ak92501) May 28, 2021
pdf: https://t.co/SOIqFhHleW
abs: https://t.co/nmhinD6kXK
demo: https://t.co/QULIeN628P
a 4-billion-parameter Transformer with VQ-VAE tokenizer, achieves a new SOTA FID on blurred MS COCO pic.twitter.com/hvXheo5cYP
🌲 Introducing TensorFlow Decision Forests, a new library you can use to train popular models like Random Forests and Gradient Boosted Trees easily with Keras.
— TensorFlow (@TensorFlow) May 27, 2021
Learn more → https://t.co/corTG7WLDT pic.twitter.com/Ut26dl4bDX
One of the most frustrating parts of interviewing as a data scientist is that hiring managers have wildly different expectations for the skillset.
— ChrisAlbon.com (@chrisalbon) May 27, 2021
Some want a BI analyst, some want a scientist, some want an MLE etc.
I wish "data scientist" would title-split into sub-categories. https://t.co/F1TIe9irE3
Calculating standard deviation is a great way to see the variability in a dataset. If you have the means, I highly recommend it.
— Caitlin Hudon 👩💻 (@beeonaposy) May 27, 2021
Despite all the media, academic, and societal interest in AI Ethics—and the clear gaps in what companies are currently doing—this FICO Responsible AI report suggests AI Ethics isn’t a priority for executives at 3/4 of companies: https://t.co/Phl8M907mP pic.twitter.com/zKnLwfUSi2
— Christopher Manning (@chrmanning) May 26, 2021
Introducing a simple one-stage approach for automated text-to-image generation that achieves state-of-the-art performance on #LocalizedNarratives using only image-text pairs — no segmentation or bounding box data needed. Learn how it’s done below: https://t.co/SPMbJaVvAN
— Google AI (@GoogleAI) May 26, 2021
People with certain jobs tend to marry others with some other job. Here are the jobs that tend to marry together the mostest. https://t.co/gjqHO3ytZ3 pic.twitter.com/FQ0xzdsL90
— Nathan Yau (@flowingdata) May 26, 2021
High-Frequency aware Perceptual Image Enhancement
— AK (@ak92501) May 26, 2021
pdf: https://t.co/1XZkAYnzrT
abs: https://t.co/sevT4gbmwu pic.twitter.com/zumPyikSzP
once again, https://t.co/hHl0PO5nuc pic.twitter.com/BMKZr7jXGF
— fasterthanlime 🌌 (@fasterthanlime) May 26, 2021
Gallup asks people around the world whether they have someone to count on for help in times of trouble.
— Max Roser (@MaxCRoser) May 25, 2021
– The map shows the share that answered 'No'.
– The plot below shows the share that answered 'No' in relation to the average income in the country. pic.twitter.com/qTYZBCvd3L
ICYDK, @Gradio is a very neat Python SDK to create simple demos around ML models.
— Hugging Face (@huggingface) May 25, 2021
In Gradio 2.0, you can wrap any huggingface model into a demo interface in 1 line of code 🔥
Read the tutorial from @abidlabs on our blog here ➡️ https://t.co/T5QBe9Znia pic.twitter.com/vHyc3b2ayf
